GPT-4.1 nano
GPT-4.1 nano is the fastest and cheapest tier of OpenAI's GPT-4.1 series, built for tasks that demand low latency.
input · usd / 1m tok
$0.10
output · usd / 1m tok
$0.40
context window
1mtokens
modalities · in → out
takes text and image in, gives text out
pricing
base api ratesusd per 1m tokens
- input
- $0.10
- output
- $0.40
- cache read
- $0.025
providers
OpenAI hosts GPT-4.1 nano. Impossibl routes your request intelligently and handles failover automatically when a provider is down.
- OpenAI
specifications
takes text and image in, gives text outopenai/gpt-4.1-nano
- creatorOpenAI
- model typeText generation
- context window1,000,000 tokens
- maximum outputnot published
- input
takes text and image in, gives text out
- outputtext
- tool callingnot verified
- releasedapr 14, 2025
- endpoint
/v1/chat/completions
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
try it · your prompt, this model, live
# responses API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["IMPOSSIBL_API_KEY"],
base_url="https://api.impossibl.com/v1",
)
resp = client.responses.create(
model="openai/gpt-4.1-nano",
input="",
)
print(resp.output_text)
edit the prompt, then run
benchmarks
intelligence index
7.8#84 of 90 models on the gateway
- coding index11.1#59 of 60
- omniscience-57.6#83 of 86
- gpqa51.2%#84 of 88
- humanity’s last exam3.8%#85 of 89
- terminal-bench v2.13.7%#56 of 57
- GPQA51.2%
- MMMU-Pro40.1%
- LiveCodeBench32.6%
- IFBench32.0%
- AIME 202524.0%
- AA-LCR20.3%
- Tau217.3%
- Terminal-Bench Hard3.8%
- Humanity’s Last Exam3.8%
- Terminal-Bench v2.13.7%
- Tau Banking3.5%
- CritPt0.0%
- Intelligence Index7.82
- Omniscience Index-57.58
- GDPval Elo12.78
- coding index (API)11.1
- intelligence index (API)7.8
each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-09-11.
compare GPT-4.1 nano with other models
frontier labs and open weights, best-ranked firstusd / 1m tok · in / out
- anthropic/claude-fable-5-1$10.00 / $50.00compare →
- meta/muse-spark-1.3$1.25 / $4.25compare →
- zai/glm-5.3$1.40 / $4.40compare →
- xai/grok-4.6$2.00 / $6.00compare →
frequently asked questions
What is GPT-4.1 nano?
GPT-4.1 nano is the fastest and cheapest tier of OpenAI's GPT-4.1 series, built for tasks that demand low latency. It suits classification, autocompletion, and other high-volume work, trading the flagship's depth for speed while retaining the family's long-context support.
How much does GPT-4.1 nano cost?
GPT-4.1 nano costs $0.10 per million input tokens and $0.40 per million output tokens through the Impossibl API. Cache reads cost $0.025 per million tokens. All rates are in USD.
What is the context length of GPT-4.1 nano?
GPT-4.1 nano has a 1,000,000-token context window through the Impossibl API.
What inputs and outputs does GPT-4.1 nano support?
GPT-4.1 nano accepts text and image as input. GPT-4.1 nano returns text.
How do I use GPT-4.1 nano through an API?
GPT-4.1 nano is available through the Impossibl API. Use openai/gpt-4.1-nano as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
When was GPT-4.1 nano released?
OpenAI released GPT-4.1 nano on April 14, 2025.
this page describes GPT-4.1 nano as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.
view the source catalog ↗model as markdown ↗report a correction →